INDEX

Explanations

terms related to mapping and its various forms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

providedIn

-0.89

 defaultstate

-0.81

 SEDS

-0.70

UnusedPrivate

-0.67

 DialogResult

-0.66

 sumpay

-0.65

Personensuche

-0.65

 actionTypes

-0.63

GenerationType

-0.63

يكب

-0.63

POSITIVE LOGITS

 maps

2.63

map

2.34

 Maps

2.28

 mapping

2.19

 mapped

2.01

 Mapping

2.00

maps

1.98

map

1.93

 mappings

1.90

Maps

1.89

Activations Density 0.056%

terms related to mapping and its various forms

No Comments

No Known Activations